Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 63 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0452. Min Act: -0.0005

Data Index: 1158612 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0307. Min Act: -0.0005

Data Index: 887693 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0340. Min Act: -0.0005

Data Index: 957042 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0313. Min Act: -0.0005

Data Index: 1144459 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0312. Min Act: -0.0005

Data Index: 1105194 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0296. Min Act: -0.0005

Data Index: 284522 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0290. Min Act: -0.0005

Data Index: 276278 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0298. Min Act: -0.0005

Data Index: 593931 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0259. Min Act: -0.0005

Data Index: 822547 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0288. Min Act: -0.0005

Data Index: 942304 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0281. Min Act: -0.0005

Data Index: 321751 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0275. Min Act: -0.0004

Data Index: 990295 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0300. Min Act: -0.0005

Data Index: 567655 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0302. Min Act: -0.0005

Data Index: 534565 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0285. Min Act: -0.0005

Data Index: 571510 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0278. Min Act: -0.0005

Data Index: 265378 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0290. Min Act: -0.0005

Data Index: 1225137 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0275. Min Act: -0.0005

Data Index: 1147017 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0259. Min Act: -0.0005

Data Index: 775918 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0286. Min Act: -0.0005

Data Index: 752533 (C4 (Web Text))

Max Activating Token Index: 810